检索结果-内蒙古大学图书馆

Contemporary computing and Communications (InC4), IEEE International Conference on

作者： Kamred Udham Singh Niharika Singh Varun Chaudhary Deepika Paliwal Teekam Singh Amit kumar Dewangan School of Computing Graphic Era Hill University Dehradun India IMS Engineering College Ghaziabad Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India G.L. Bajaj Institute of Technology & Management Greater Noida Geetanjali Institute of Technical Studies Dabok Udaipur Department of Information Technology Guru Ghasidas Vishwavidyalaya Bilaspur India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383669

Understanding social media sarcasm is a difficult but crucial NLP issue. Machine learning (ML) algorithms are needed to effectively discern sarcastic undertones in text due to its contextual and linguistic complexity. Traditional ML models distinguish sarcasm from sincerity via sentiment analysis, context-specific variables, and language markers. As online communication evolves, more complex technologies are needed to understand language's subtleties. The merging of deep learning (DL) approaches with contextual embedding has greatly improved sarcasm detection systems, allowing them to analyze text more precisely and contextually. The CSOA-GNN model, which combines the Chicken Swarm Optimization Algorithm (CSOA) with Graph Neural Networks to identify sarcasm. After rigorous data pre-processing, the model embeds words using TF-IDF (Term Frequency-Inverse Document Frequency). Sarcasm's unique language traits are vectorized for ML analysis using this method. GNN is then used to classify. Its ability to map out and grasp the complicated network of contextual links and dependencies among words inside sentences improves the model's sarcasm detection accuracy. CSOA is crucial to optimizing GNN performance in this model. CSOA optimizes the GNN hyperparameters to match social media text's sarcastic expressions. This unique technique relies on GNN-based classification, CSOA-based parameter optimization, and TF-IDF word embeddings, which provide encouraging results that demonstrate their efficacy. As they increase social media sarcasm detection accuracy and advance NLP. This study introduces the CSOA-GNN paradigm, enabling more advanced, contextually aware, and nuanced language interpretation systems. It advances our understanding of the complicated world of online communication, where sarcasm, frequently laced with nuanced indications and contextual richness, is a constant challenge. This model shows that powerful optimization methods may be integrated with neural network topo

关键词： Sentiment analysis Accuracy Social networking (online) Graph neural networks Classification algorithms Topology Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Acoustic Sensor Networks: An Energy Efficient Grey Wolf Optimization Algorithm development for underwater networks 1

Acoustic Sensor Networks: An Energy Efficient Grey Wolf Opti...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Vanitha, V. Barve, Amit Singh, Arjun Javanthi, R. Dwivedi, Rakesh Kumar Vishwath, N.C. Ajay India Department of CSE PIET Parul University Gujarat Vadodara India Dev Bhoomi Uttarakhand University Department of School of Engineering Uttarakhand Dehradun India Department of Computer Science & IT Bangalore India Faculty of Engineering Teer Thanker Mahaveer University Department of Computing Sciences & IT Uttar Pradesh Moradabad India Parul University Aeronautical Department Parul Institute of Engineering and Technology India

ISBN: (纸本)9781665456876

Underground wireless sensors (UWASNs) are intended to serve a range of needs for global research and marine management. For some of these uses, the network of several sensors is positioned underwater at various depths. These nodes need multi-hop transmission, which is made possible by efficient routing design, but the seafloor located IoT devices seem to be unable to connect without a hitch to any network that are near to the base level. The occurrence of uninhabited areas along the route may also have an impact on the overall efficacy of UWASNs. Therefore, the empty zone may be avoided by choosing the optimum introduction. The optimum routing node is chosen based on the strength of the connection, average energy, depth fluctuation, and length difference. An orientation is another factor that is taken into account while selecting the optimum forwarder node. Using the theory of the maned wolf optimization issue, the best course of action is determined. The suggested approach extends the life of the network and also balances network energy by avoiding the vacant zone. Utilizing the Matlab program, power and depths variability pragmatic void avoidance systems, and analyzing deep and moving area split knowledge routes, the suggested work is evaluated. In this study, a 180-unit setup with a configurable radio range of up to 1000 m yields a 96% total packet delivery ratio. This brings down the mean number of deceased nodes and the end-to-end time, respectively, to 53% and 145. This strategy also decreases latency and lengthens the overall network lifespan. Additionally, this strategy leads to the production of digital data books falling by 55%. In addition, the results section provides a variety of additional evaluation standards. © 2022 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Student’s Performance Prediction Using Machine Learning Algorithms- A Comparative Study

Student’s Performance Prediction Using Machine Learning Alg...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Varun Kadu Pawan Kumar Mishra Sarthak Dandhare Jagdish Chandra Patni Palash Chandel Soham Pathak Nilesh Bahadure Symbiosis Institute of Technology Nagpur Campus SIU Pune India Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Dept. of CSE Alliance School of Advance Computing Alliance University Bengaluru Karnataka India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

Predicting and enhancing student performance has been a crucial topic of concentration in education amid the quick development of technology and the increasing need for higher-quality instruction. The use of machine learning technology to forecast pupils’ academic success is covered in detail in this study report. This research project examined several prediction models that reliably predict students’ performance according to a range of extracurricular and academic attributes. An overview of machine learning methods is given in this paper to automate the process of predicting students’ academic performance and extracting outcomes.

关键词： Technological innovation Machine learning algorithms Computational modeling Education Machine learning Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Feature Rotation Invariance Learning for Point Cloud Analysis

Feature Rotation Invariance Learning for Point Cloud Analysi...

引用

Smart World Congress (SWC), IEEE

作者： Lu Shi Qi Cao Guoqing Zhang Jin Yi Yansen Huang Yigang Cen State Key Laboratory of Advanced Rail Autonomous Operation the School of Computer Science and Technology and Visual Intellgence +X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University Beijing China the School of Computing Science University of Glasgow Singapore With the Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education the State Key Laboratory of Advanced Rail Autonomous Operation and the School of Computer and Information Technology Beijing Jiaotong University Beijing China the College of Civil Engineering Guizhou University Guizhou Lianjian Civil Engineering Quality Testing Monitoring Center Co. LTD Guizhou China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

While deep learning has significantly advanced point cloud analysis, extracting effective features from their disordered structure remains challenging. Existing approaches often rely on complex network architectures or manual feature engineering to achieve rotation invariance, which increases inference latency. This paper offers a novel perspective on this challenge, showing that rotation-sensitive models can achieve performance comparable to rotation-invariant models when trained with rotation-augmented data. Given the significant differences in the feature distributions of rotation-sensitive and rotation-invariant models, we propose Feature Rotation Invariance Learning (FRIL), a framework that leverages Distance Metric Learning and rotation-based constraints to help rotation-sensitive models extract rotation-invariant features. This approach eliminates the need for additional modules, enabling robust performance against rotations. Extensive experiments demonstrate that FRIL consistently outperforms existing rotation-invariant methods across various visual tasks.

关键词： Point cloud compression Representation learning Analytical models Solid modeling Visualization Three-dimensional displays Semantics Cloning Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Activities Prediction of Drug Molecules by Using Automated Model Building with Descriptor Selection 1st

Activities Prediction of Drug Molecules by Using Automated M...

引用

1st BenchCouncil International Federated Intelligent computing and Block Chain Conferences, FICC 2020

作者： Liu, Yue Tian, Wenjie Zhang, Hao School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai China Shanghai Engineering Research Center of Intelligent Computing System Shanghai200444 China Shanghai Chempartner Co. Ltd. Shanghai201203 China

ISBN: (纸本)9789811611599

Machine learning is a powerful tool for simulating the quantitative structure activity relationship in drug discovery (QSAR). However, descriptor selection and model optimization remain two of most challenging tasks for domain experts to construct high-quality QSAR model. Therefore, we propose a QSAR-special automated machine learning method incorporating Automated Descriptor Selection with Automated Model Building (ADSMB) to efficiently and automatically build high-quality QSAR model. Automated Descriptor Selection provides a QSAR-special molecular descriptor selection mechanism to automatically obtain the descriptors without unique value, redundancy and low importance in QSAR dataset. Based on these QSAR-special descriptors, Automated Model Building constructs high-quality ensemble model of molecular descriptors and target activities under Bayesian optimization through Auto-Sklearn. Finally, we conduct experimental evaluation for our proposed method on Mutagenicity dataset. The results show ADSMB can obtain better and stable performance than the competing methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Water Tank Management and Control System

Cloud-based Water Tank Management and Control System

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： CH Chandra Sekhar Vedanarayanan. V K. Vijayalakshmi Madona B Sahaai A. Sanyasi Rao S. Murugan Department of Computer Science Engineering A.P Residential Degree College Narasaraopet Andhra Pradesh India Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Veltech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamil Nadu India Department of Electronics and Communication Engineering Balaji Institute of Technology & Science Warangal Telangana India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

The solution to water constraints and the advancement of sustainable resource usage is effective water management. This research presents a cloud-based water tank management system that uses Raspberry Pi, sensors, a Wi-Fi connection, and the ThingSpeak platform for real-time monitoring and control. A Raspberry Pi flexible single-board computer controls the system. To keep updated on how much water is in each storage tank, use various sensors, including ultrasonic and pressure sensors. The data from these sensors is sent to and processed by a Raspberry Pi. Raspberry Pi can now communicate with a cloud server after being connected to a local network through Wi-Fi. The ability to remote access and monitor the water storage system from afar is made possible by this link. The data is stored, analyzed, and shown using ThingSpeak, a cloud-based IoT platform. It has a simple interface that can be used to monitor water levels in real-time, examine data from the past, and develop findings that can be used to manage water resources better. Several benefits can be acquired by using the suggested system. Water levels can be monitored in real-time, making it possible to identify problems like leaks or overflow fast as events occur. Users can check in on their water storage tanks from anywhere the happen to be due to this feature's remote access capabilities. For more effective water management, less water waste, and increased use of available water resources in a sustainable process. Cloud infrastructure helps reduce the problems caused by water shortages by promoting efficient water management and encouraging water use in a sustainable method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning from Multi-Perception Features for Real-Word Image Super-resolution

arXiv

引用

arXiv 2023年

作者： Niu, Axi Zhang, Kang Pham, Trung X. Wang, Pei Sun, Jinqiu Kweon, In So Zhang, Yanning The School of Computer Science Northwestern Polytechnical University Xi’an710072 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710072 China The School of Electrical Engineering Korea Advanced Institute of Science and Technology Korea Republic of The School of Astronautics Northwestern Polytechnical University Xi’an710072 China

Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation, making them less applicable to real-world LR images. On the other hand, blind-based methods are often limited by their fixed single perception information, which hinders their ability to handle diverse perceptual characteristics. To overcome this limitation, we propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information and a series of newly-designed Cross-Perception Blocks (CPB) to combine this information for effective super-resolution reconstruction. Additionally, we introduce a contrastive regularization term (CR) that improves the model’s learning capability by using newly generated HR and LR images as positive and negative samples for ground truth HR. Experimental results on challenging real-world SR datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in both qualitative and quantitative measures. © 2023, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

FDPS: A YOLO-Based Framework for Fire Detection and Prevention 1st

FDPS: A YOLO-Based Framework for Fire Detection and Preventi...

引用

1st International Conference on Intelligent Systems and Data science, ISDS 2023

作者： Le, Tan Duy Nguyen, Huynh Phuong Thanh Tran, Duc Tri Mai, An Huynh, Kha Tu Nguyen, Sinh Van School of Computer Science and Engineering International University Ho Chi Minh City Ho Chi Minh Viet Nam Japan Advanced Institute of Science and Technology Ishikawa Nomi Japan Vietnam National University Ho Chi Minh City Ho Chi Minh Viet Nam

ISBN: (纸本)9789819976652

Accidental fires or explosions pose a significantly threat to human life and social safety, making them a major concern for humanity. In this study, we propose FDPS, an inexpensive and efficient machine learning-based framework for the early detection and extinguishing of small fires using a minimal amount of Internet of Things equipment, such as a NodeMCU, camera, and pump. The system functions through two primary phases: fire detection and fire extinguishing. During the initial phase, the camera rotates horizontally while continually analyzing images that were collected and processed by a pre-trained YOLO model to detect the presence of fire. The second phase activates when the fire is detected, and the system transmits signals to adjust the camera’s angle and activates the water pump, which then extinguishes the fire. Our experiment results demonstrate that the proposed framework can accurately detect fires, achieving an average precision of nearly 90% and running inference in about five milliseconds. By detecting fires quickly, emergency responders can be alerted to respond promptly, potentially reducing property damage and saving lives. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Crowd Counting via Density Agency

arXiv

引用

arXiv 2022年

作者： Lin, Hui Ma, Zhiheng Hong, Xiaopeng Wang, Yaowei Su, Zhou School of Cyber Science and Engineering Xi’an Jiaotong University China Shenzhen Institute of Advanced Technology Chinese Academy of Science China School of Computer Science and Technology Harbin Institute of Technology China Peng Cheng Laboratory China Xi’an Jiaotong University China

In this paper, we propose a new agency-guided semi-supervised counting approach. First, we build a learnable auxiliary structure, namely the density agency to bring the recognized foreground regional features close to corresponding density sub-classes (agents) and push away background ones. Second, we propose a density-guided contrastive learning loss to consolidate the backbone feature extractor. Third, we build a regression head by using a transformer structure to refine the foreground features further. Finally, an efficient noise depression loss is provided to minimize the negative influence of annotation noises. Extensive experiments on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised counting methods by a large margin. Code is available. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Data Security: Integrating Elliptic Galois Cryptography with Matrix XOR Steganography and Adaptive Firefly Optimization

Enhancing IoT Data Security: Integrating Elliptic Galois Cry...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： P. Chinnasamy Ramesh Kumar Ayyasamy K. Anuradha Irfan Alam Deveendra Menon Narayanan Nair Ajmeera Kiran Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Malaysia Department of CSE (AI &ML) CVR College of Engineering Telangana India Cyber Security and Digital Forensics Division SCAI VIT Bhopal University Kothari Kalan Sehore India Department of Computer Science and Engineering MLR Institute of Technology Hdyerabad India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

Securing the uninterrupted data flow is crucial in the fast-advancing Internet of Things (IoT) market. This work investigates the incorporation of elliptic Galois cryptography and matrix XOR coding steganography to improve data security. The suggested solution employs the elliptic Galois cryptography protocol to encrypt sensitive data from diverse medical records. The private information is embedded within images through the matrix XOR encoding steganography algorithm. The Adaptive Firefly optimization approach is used to improve the efficiency of utilizing cover blocks for steganography. The effectiveness of the proposed technique is evaluated using various modern approaches. We analyze the efficiency and security of the proposed approach by comparing it with a previous hybrid method employing the New York State Department of Health dataset. The results unequivocally validate that our approach offers enhanced safety in Internet of Things (IoT) applications.

关键词： Steganography Protocols Image coding Elliptic curve cryptography Data transfer Encoding Safety Internet of Things Galois fields Optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：